Model reference · open weights
InternVL2_5 is an open-weight language model from OpenGVLab, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
InternVL25-4B [\[📂 GitHub\]](https://github.com/OpenGVLab/InternVL) [\[📜 InternVL 1.0\]](https://huggingface.co/papers/2312.14238) [\[📜 InternVL 1.5\]](https://huggingface.co/papers/2404.16821) [\[📜 Mini-InternVL\]](https://arxiv.org/abs/2410.16261) [\[📜 InternVL 2.5\]](https://huggingface.co/papers/2412.05271) [\[🆕 Blog\]](https://internvl.github.io/blog/) [\[🗨️ Chat Demo\]](https://internvl.opengvlab.com/) [\[🤗 HF Demo\]](https://huggingface.co/spaces/OpenGVLab/InternVL) [\[🚀 Quick Start\]](#quick-start) [\[📖 Documents\]](https://internvl.readthedocs.io/en/latest/) Introduction We are excited to introduce InternVL 2.5, an advanced multimodal large language model (MLLM) series that builds upon InternVL 2.0, maintaining its core model architecture while introducing significant enhancements in training and testing strategies as well as data quality. InternVL 2.5 Family In the following table, we provide an overview of the InternVL 2.5 series. Model Architecture As shown in the following figure, InternVL 2.5 retains the same model architecture as its predecessors, InternVL 1.5 and 2.0, following the "ViT-MLP-LLM" paradigm. In this new version, we integrate a newly incrementally pre-trained InternViT with various pre-trained LLMs, including InternLM 2.5 and Qwen 2.5, using a randomly initialized MLP projector. As in the previous version, we applied a pixel unshuffle operation, reducing the number of visual tokens to one-quarter of the original. Besides, we adopted a similar dynamic resolution strategy as InternVL 1.5, dividing images into tiles of 448×448 pixels. The key difference, starting from InternVL 2.0, is that we additionally introduced support for multi-image and video data. Training Strategy Dynamic High-Resolution for Multimodal Data In InternVL 2.0 and 2.5, we extend the dynamic high-resolution training approach, enhancing its capabilities to handle multi-image and video datasets. - For single-image datasets, the total number of tiles nmax are allocated to a single image for maximum resolution. Visual tokens are enclosed in <img and </img tags. - For multi-image datasets, the total number of tiles nmax are distributed across all images in a sample. Each
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | OpenGVLab |
|---|---|
| Type | Language models |
| Parameters (lead) | 3.7B |
| Variants | 4 |
| Runs with | transformers |
| Based on | OpenGVLab/InternViT-300M-448px-V2_5, Qwen/Qwen2.5-3B-Instruct |
| Released | 2024-11-20 |
| Popularity | 260k downloads / month |
| Likes | 107 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
Using it via the API
Once AxForge deploys internvl2-5 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (internvl2-5 below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"internvl2-5","messages":[{"role":"user","content":"Hello"}]}'
Details
Languages
Trained / evaluated on
Tags
Papers
Licence
Open weights under mit — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗